Add more GPUs to the roofline hardware list

Open Beginner friendly
  • Is something wrong?
#5 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
90/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Active
Tech stack
python, pytorch
Domain
machine-learning

Research direction

Read the HARDWARE dict in src/bitsmith/bench/roofline.py and the existing checks in tests/unit/test_bench.py. Use official datasheets to add RTX 4060, RTX 4070, L4, A10G and L40S with memory bandwidth and peak FP16 throughput, then add a test for one entry. Done when bitsmith info lists the GPUs, bitsmith roofline --hardware <new> works, and the PR description links each datasheet.

Written by the indexing model from the issue text.

Description

area: benchmarks good first issue

bitsmith roofline estimates decode speed from a GPU's memory bandwidth and peak FP16
throughput. The list currently has RTX 3050 Laptop, T4, RTX 3090, RTX 4090, A100, H100 and
M2 Pro.

Task: add common GPUs such as RTX 4060, RTX 4070, L4, A10G and L40S, using numbers from
the official datasheets.

Files

  • src/bitsmith/bench/roofline.py: the HARDWARE dict
  • tests/unit/test_bench.py: add a check for one of the new entries

Done when bitsmith info lists the new GPUs, bitsmith roofline --hardware <new> works,
and the PR description links the datasheet for each number.

Dominant language
Python
Stars
0
Forks
0
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from yashwanthdevavarapu/bitsmith

All issues in yashwanthdevavarapu/bitsmith

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.